system

Abstract

An object of a system according to an embodiment is to automate and streamline a return task in an EC operation.SOLUTION: A system according to an embodiment includes a return reason determination unit, a commodity state determination unit, a return possibility determination unit, a refund processing unit, and a data analysis unit. The return reason determination unit determines the reason for return based on the content input by the customer. The commodity state determination unit determines a state of the commodity based on the reason for return determined by the reason for return determination unit. The return possibility determination unit determines whether to return or refund the commodity based on the state of the commodity determined by the commodity state determination unit. The refund processing unit automatically executes a refund process or an exchange process based on the reason for return determined by the return possibility determination unit. The data analysis unit analyzes data such as the reason for return and the customer attributes, examines measures for reducing the return rate, and plans measures for improving customer satisfaction.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, returns procedures in e-commerce operations were complicated, time-consuming, and costly.

[0005] The system according to the embodiment aims to automate and streamline return operations in e-commerce operations. [Means for solving the problem]

[0006] The system according to the embodiment includes a return reason determination unit, a product condition determination unit, a return acceptance determination unit, a refund processing unit, and a data analysis unit. The return reason determination unit determines the reason for return from the customer's input. The product condition determination unit determines the condition of the product based on the reason for return determined by the return reason determination unit. The return acceptance determination unit determines whether to accept a return or refund based on the condition of the product determined by the product condition determination unit. The refund processing unit automatically executes refund processing or exchange processing based on the reason for return determined by the return acceptance determination unit. The data analysis unit analyzes data such as the reason for return and customer attributes, considers measures to reduce the return rate, and plans measures to improve customer satisfaction. [Effects of the Invention]

[0007] The system according to the embodiment can automate and streamline return operations in e-commerce operations. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The return process automation system according to an embodiment of the present invention is a system that automatically determines the reason for return from the customer's input, automatically determines the condition of the product using image recognition technology, and uses AI to determine whether to allow a return or refund based on the reason for return and the condition of the product, and automatically processes the refund or exchange. As a result, the return process automation system can significantly reduce the time and cost of return operations and improve customer satisfaction.

[0029] The return process automation system according to the embodiment includes a return reason determination unit, a product condition determination unit, a return acceptance determination unit, a refund processing unit, and a data analysis unit. The return reason determination unit determines the reason for return based on the customer's input. For example, if a customer inputs "The size doesn't fit," the generation AI analyzes the information and classifies the reason for return as "Size mismatch." Similarly, if a customer inputs "The product is damaged," the generation AI analyzes the information and classifies the reason for return as "Product damaged." Similarly, if a customer inputs "It's different from what I expected," the generation AI analyzes the information and classifies the reason for return as "Different from what I expected." The product condition determination unit determines the condition of the product using image recognition technology. For example, the generation AI analyzes product images uploaded by customers and determines the product's condition as "New." Similarly, the generation AI analyzes product images uploaded by customers and determines the product's condition as "Used." Similarly, the generation AI analyzes product images uploaded by customers and determines the product's condition as "Damaged." The return acceptance / refund decision unit determines whether to accept a return or refund based on the reason for return and the condition of the product. For example, if the reason for return is "wrong size" and the product condition is "new," the generation AI will accept the return and refund. The generation AI will also accept the return and refund if the reason for return is "damaged product" and the product condition is "damaged." The generation AI will also reject the return and refund if the reason for return is "different from expected" and the product condition is "used." The refund processing unit automatically executes refund and exchange processes based on the reason for return. For example, if the reason for return is "wrong size" and the return is permitted, the generation AI will automatically process a refund. The generation AI will also automatically process an exchange if the reason for return is "damaged product" and the return is permitted. The data analysis unit analyzes data such as return reasons and customer attributes, considers measures to reduce return rates, and develops measures to improve customer satisfaction. For example, if a particular product has a high number of returns, the AI ​​will suggest improving the size or description of that product. Also, if the reason for return is "different from the product description," the AI ​​will suggest making the product description more detailed.Furthermore, the generation AI plans marketing measures for specific customer segments based on customer attributes. As a result, the return process automation system according to the embodiment can significantly reduce the time and cost of return processes and improve customer satisfaction.

[0030] When analyzing a customer's input, the return reason determination unit also references past purchase history and review content, allowing for more accurate determination of return reasons. For example, when the generation AI analyzes a customer's input, the return reason determination unit references past purchase history and, if the same product has been purchased multiple times, checks whether the return reason is consistent. For example, if the reason for returning the same product in the past was "wrong size," it is likely that the reason will be the same this time. Furthermore, when analyzing a customer's input, the return reason determination unit references review content to check how other customers have rated the same product. For example, if another customer reviews the product as "not fitting," the return reason can be classified as "wrong size" based on that information. Furthermore, when analyzing a customer's input, the return reason determination unit integrates past purchase history and review content to more accurately determine return reasons. For example, the return reason can be classified as "wrong size" based on past purchase history and review content. By referencing past purchase history and review content, the accuracy of return reason determination can be improved.

[0031] When determining the reason for return, the return reason determination unit can improve the accuracy of determination by asking questions in real time in response to the customer's input and collecting additional information. For example, the return reason determination unit has the generation AI analyze the customer's input and ask questions in real time if there are any ambiguities. For example, if the customer inputs "the size doesn't fit," the unit will ask "which part specifically doesn't fit" to collect more detailed information. The return reason determination unit also analyzes the customer's input and asks questions in real time if additional information is required. For example, if the customer inputs "the product is damaged," the unit will ask "which part is damaged" to collect more detailed information. The return reason determination unit also improves the accuracy of determination of the reason for return by having the generation AI analyze the customer's input and collect additional information. For example, the unit classifies the reason for return as "incompatible size" based on the additional information. In this way, by asking questions in real time, the accuracy of determination of the reason for return is improved.

[0032] When determining the reason for return, the return reason determination unit can also accept voice input and determine the reason for return using voice recognition technology. In the return reason determination unit, for example, the generation AI accepts voice input and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The size doesn't fit," the voice data is converted into text and the reason for return is classified as "incompatible size." In addition, the return reason determination unit accepts voice input using the generation AI and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The product is damaged," the voice data is converted into text and the reason for return is classified as "damaged product." In addition, the return reason determination unit can more flexibly determine the reason for return by having the generation AI accept voice input and analyze the customer's reason for return using voice recognition technology. For example, the reason for return is classified as "incompatible size" based on the voice input. In this way, by accepting voice input, the reason for return can be more flexibly determined.

[0033] When determining reasons for returns, the return reason determination unit can crawl customer comments on other e-commerce sites and social media to collect related information and use it for determination. For example, the generation AI crawls customer comments on other e-commerce sites and social media to collect related information. For example, if another customer comments about the same product that "the size doesn't fit," the return reason determination unit can classify the reason for return as "mismatched size" based on that information. The return reason determination unit also crawls customer comments on other e-commerce sites and social media to collect related information. For example, if another customer comments about the same product that "the product is damaged," the return reason determination unit can classify the reason for return as "damaged product" based on that information. The return reason determination unit also improves the accuracy of determining reasons for returns by crawling customer comments on other e-commerce sites and social media to collect related information. For example, the return reason determination unit can classify the reason for return as "mismatched size" based on information on other e-commerce sites and social media. By utilizing information from other e-commerce sites and social media, the accuracy of determining reasons for returns can be improved.

[0034] When determining the condition of a product, the product condition determination unit can increase the reliability of the determination by also referring to quality information provided by the product's manufacturer or seller. For example, the generation AI in the product condition determination unit determines the condition of the product by referring to quality information provided by the product's manufacturer or seller. For example, the product condition is evaluated based on quality standards provided by the manufacturer. The product condition determination unit also determines the condition of the product by referring to quality information provided by the product's manufacturer or seller. For example, the product condition is evaluated based on quality information provided by the seller. The product condition determination unit also increases the reliability of the determination by referring to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition is determined to be "new" based on quality information from the manufacturer or seller. In this way, by referring to quality information from the manufacturer or seller, the reliability of the determination of the product's condition is improved.

[0035] When determining the condition of a product, the product condition determination unit can also analyze video data and determine the condition of the product based on dynamic information. For example, the generation AI analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video to evaluate the condition. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video to evaluate the condition. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product based on dynamic information. For example, the product condition is determined to be "new" based on the video data. This makes it possible to more accurately determine the condition of a product by analyzing the video data.

[0036] When determining the condition of a product, the product condition determination unit can maintain consistency in its determination by referencing data from when other customers returned the same product. For example, the product condition determination unit determines the condition of the product by referencing data from when the generation AI returned the same product. For example, if the same product was returned in the past due to "dissatisfied quality," the current condition of the product is evaluated based on that information. The product condition determination unit also determines the condition of the product by referencing data from when other customers returned the same product. For example, if the same product was returned in the past due to "size mismatch," the current condition of the product is evaluated based on that information. The product condition determination unit also maintains consistency in its determination by referencing data from when other customers returned the same product. For example, the product condition determination unit determines the condition of the product as "new" based on the return data of other customers. This maintains consistency in the determination of the product condition by referencing the return data of other customers.

[0037] The return acceptance / refund decision unit can learn from past return / refund data to make more accurate decisions when determining whether to accept a return or refund. For example, if the same product was previously returned due to "wrong size," the return acceptance / refund decision unit can use that information to determine whether to accept a return or refund. The return acceptance / refund decision unit can also learn from past return / refund data to determine whether to accept a return or refund. For example, if the same product was previously returned due to "unsatisfactory quality," the return acceptance / refund decision unit can use that information to determine whether to accept a return or refund. The return acceptance / refund decision unit can also improve its decision accuracy by learning from past return / refund data to determine whether to accept a return or refund. For example, it can determine whether to accept a return or refund based on past data. Learning from past data improves the accuracy of return / refund decisions.

[0038] When determining whether to allow a return or refund, the return acceptance determination unit can make a comprehensive decision by taking into account the customer's credit score and past transaction history. For example, the return acceptance determination unit uses the generation AI to refer to the customer's credit score and determine whether to allow a return or refund. For example, a customer with a high credit score is more likely to allow a return or refund. The return acceptance determination unit also uses the generation AI to refer to the customer's credit score and determine whether to allow a return or refund. For example, a customer with a low credit score is more likely to refuse a return or refund. The return acceptance determination unit also uses the generation AI to make a comprehensive decision by taking into account the customer's credit score and past transaction history. For example, it determines whether to allow a return or refund based on the credit score and transaction history. This allows for a more comprehensive decision by taking into account the customer's credit score and transaction history.

[0039] When determining whether to allow returns or refunds, the return acceptance determination unit can refer to the return policies and industry standards of other e-commerce sites and adjust its criteria. For example, the generation AI may refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "wrong size," the generation AI may use that information to determine whether to allow returns or refunds. The return acceptance determination unit may also refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "damaged product," the generation AI may use that information to determine whether to allow returns or refunds. The return acceptance determination unit may also refer to the return policies and industry standards of other e-commerce sites to adjust its criteria. For example, the generation AI may determine whether to allow returns or refunds based on information from other e-commerce sites and industry standards. This makes it possible to adjust the criteria by referring to other e-commerce sites and industry standards.

[0040] When automatically executing refund or exchange processing, the refund processing unit can consider multiple payment methods and delivery methods and select the optimal method. In the refund processing unit, for example, the generation AI considers multiple payment methods and selects the optimal refund method. For example, in the case of credit card payment, it selects refund to the credit card. In addition, the refund processing unit considers multiple payment methods and selects the optimal refund method. For example, in the case of bank transfer, it selects refund to a bank account. In addition, the refund processing unit efficiently performs refund and exchange processing by considering multiple payment methods and delivery methods and selecting the optimal method. For example, it selects the optimal refund method based on the payment method and delivery method. This makes it possible to consider multiple payment methods and delivery methods and perform optimal refund and exchange processing.

[0041] When executing refund or exchange processing, the refund processing unit can perform customized processing by taking into account the customer's past transaction history and preferences. In the refund processing unit, for example, the generation AI references the customer's past transaction history and performs customized refund processing. For example, for a customer who has previously paid by credit card, it prioritizes refunding to the credit card. In addition, the refund processing unit can perform customized refund processing by taking into account the customer's past transaction history and preferences. For example, for a customer who has previously paid by bank transfer, it prioritizes refunding to a bank account. In addition, the refund processing unit can perform customized refund or exchange processing by taking into account the customer's past transaction history and preferences. For example, it selects the optimal refund method based on the transaction history and preferences. This makes it possible to perform customized refund or exchange processing by taking into account the customer's past transaction history and preferences.

[0042] The refund processing unit can improve the efficiency of processing by strengthening cooperation with other e-commerce sites and logistics companies when executing refund processing and exchange processing. In the refund processing unit, for example, the generation AI cooperates with other e-commerce sites to make refund processing more efficient. For example, it refers to the refund policies of other e-commerce sites to process refunds quickly. In addition, the refund processing unit can improve the efficiency of refund processing by strengthening cooperation with other e-commerce sites and logistics companies. For example, it refers to the refund policies of other e-commerce sites to process refunds quickly. In addition, the refund processing unit can improve the efficiency of refund processing and exchange processing by strengthening cooperation with other e-commerce sites and logistics companies. For example, it selects the optimal refund method based on information from the e-commerce site and logistics company. In this way, cooperation with other e-commerce sites and logistics companies is strengthened, thereby improving processing efficiency.

[0043] The refund processing unit can increase transparency by notifying customers of the progress status in real time when executing refund processing or exchange processing. For example, the refund processing unit builds a system in which the generation AI notifies customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer when the refund processing starts. The refund processing unit also builds a system in which the generation AI notifies customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer when the refund processing is completed. The refund processing unit also increases the transparency of the processing by having the generation AI notify customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer based on the progress status. In this way, by notifying customers of the progress status in real time, the transparency of the processing is increased.

[0044] When conducting data analysis, the data analysis unit can integrate different data sources to perform a more comprehensive analysis. For example, the generation AI integrates social media data and market data to perform data analysis. For example, it integrates customer opinions on social media with market sales data to analyze product reviews. The data analysis unit also integrates different data sources to perform data analysis. For example, it integrates customer data and sales data to analyze customer purchasing behavior. The data analysis unit also integrates different data sources to perform data analysis, making more comprehensive analysis possible. For example, it analyzes product reviews based on social media data, market data, and customer data. In this way, by integrating different data sources, more comprehensive data analysis becomes possible.

[0045] When analyzing data, the data analysis unit can predict trends using time series data and plan future measures. In the data analysis unit, for example, the generation AI uses time series data to predict trends and plan future measures. For example, sales for the next season are predicted based on past sales data. In addition, the data analysis unit uses the generation AI to predict trends using time series data and plan future measures. For example, customer behavior for the next season is predicted based on past customer behavior data. In addition, the data analysis unit uses the generation AI to predict trends using time series data and plan future measures, thereby implementing more effective measures. For example, sales trends are predicted based on time series data and marketing measures for the next season are planned. In this way, trend prediction and future measures can be planned using time series data.

[0046] When analyzing data, the data analysis department compares data from different industries and regions, allowing it to plan measures from a global perspective. For example, the generation AI in the data analysis department compares data from different industries and plans measures from a global perspective. For example, it compares data from the fashion industry and the technology industry to find common trends. The generation AI also compares data from different industries and plans measures from a global perspective. For example, it compares data from the food industry and the electronics industry to find common trends. The data analysis department also compares data from different industries and regions and plans measures from a global perspective, allowing it to implement more effective measures. For example, it plans global marketing measures based on data from different industries and regions. This makes it possible to plan measures from a global perspective by comparing data from different industries and regions.

[0047] When performing data analysis, the data analysis unit can generate visual data and present the results in a form that is visually easy to understand. For example, the data analysis unit uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand. For example, sales data is displayed as a graph. The data analysis unit also uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand. For example, customer behavior data is displayed as a chart. The data analysis unit also uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand, thereby promoting understanding of the data. For example, sales trends are analyzed based on the visual data. In this way, by generating visual data, the results of data analysis can be presented in a form that is visually easy to understand.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] When determining the reason for return, the return reason determination unit can improve the accuracy of determination by asking questions in real time in response to the customer's input and collecting additional information. For example, the generation AI analyzes the customer's input and asks questions in real time if there are any ambiguities. For example, if the customer inputs "The size doesn't fit," the unit will ask "Which part specifically doesn't fit?" to collect more detailed information. The return reason determination unit also analyzes the customer's input and asks questions in real time if additional information is required. For example, if the customer inputs "The product is damaged," the unit will ask "Which part is damaged?" to collect more detailed information. The return reason determination unit also improves the accuracy of determination of the reason for return by having the generation AI analyze the customer's input and collect additional information. For example, the unit may classify the reason for return as "inappropriate size" based on the additional information. This improves the accuracy of determination of the reason for return by asking questions in real time.

[0050] When determining the reason for return, the return reason determination unit can also accept voice input and determine the reason for return using voice recognition technology. For example, the generation AI accepts voice input and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The size doesn't fit," the voice data is converted into text and the reason for return is classified as "size mismatch." The return reason determination unit also accepts voice input using voice recognition technology and analyzes the customer's reason for return. For example, if a customer voice-inputs, "The product is damaged," the voice data is converted into text and the reason for return is classified as "product damaged." The return reason determination unit also accepts voice input using voice recognition technology, allowing for more flexible determination of return reasons. For example, the reason for return is classified as "size mismatch" based on voice input. This allows for more flexible determination of return reasons by accepting voice input.

[0051] When determining the condition of a product, the product condition determination unit can increase the reliability of the determination by also referring to quality information provided by the product's manufacturer or seller. For example, the generation AI may refer to quality information provided by the product's manufacturer or seller to determine the condition of the product. For example, the product's condition may be evaluated based on quality standards provided by the manufacturer. The product condition determination unit also increases the reliability of the determination by having the generation AI refer to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition may be evaluated based on quality information provided by the seller. The product condition determination unit also increases the reliability of the determination by having the generation AI refer to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition may be determined to be "new" based on quality information from the manufacturer or seller. In this way, by referring to quality information from the manufacturer or seller, the reliability of the determination of the product's condition is improved.

[0052] When determining the condition of a product, the product condition determination unit can also analyze video data and determine the condition of the product based on dynamic information. For example, the generation AI analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video and the condition is evaluated. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video and the condition is evaluated. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product based on dynamic information. For example, the product condition is determined to be "new" based on the video data. This makes it possible to more accurately determine the condition of a product by analyzing the video data.

[0053] When determining whether to allow returns or refunds, the return acceptance determination unit can refer to the return policies and industry standards of other e-commerce sites and adjust its criteria. For example, the generation AI can refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "wrong size," the generation AI can use that information to determine whether to allow returns or refunds at present. The return acceptance determination unit can also refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "damaged product," the generation AI can use that information to determine whether to allow returns or refunds at present. The return acceptance determination unit can also refer to the return policies and industry standards of other e-commerce sites to adjust its criteria. For example, the generation AI can determine whether to allow returns or refunds based on information from other e-commerce sites and industry standards. This makes it possible to adjust the criteria by referring to other e-commerce sites and industry standards.

[0054] The processing flow of the first embodiment will be briefly explained below.

[0055] Step 1: The return reason determination unit determines the reason for return from the customer's input. For example, if a customer inputs "The size doesn't fit," the generation AI analyzes that information and classifies the reason for return as "mismatched size." If a customer inputs "The product is damaged," the generation AI analyzes that information and classifies the reason for return as "damaged product." If a customer inputs "It's different from what I expected," the generation AI analyzes that information and classifies the reason for return as "different from what I expected." Step 2: The product condition determination unit uses image recognition technology to determine the product condition. For example, the generation AI analyzes product images uploaded by customers and determines the product condition as "new." The generation AI also analyzes product images uploaded by customers and determines the product condition as "used." The generation AI also analyzes product images uploaded by customers and determines the product condition as "damaged." Step 3: The return acceptance / refund decision unit determines whether to accept a return or refund based on the reason for return and the condition of the product. For example, if the reason for return is "wrong size" and the condition of the product is "new," the generation AI will allow the return and refund. If the reason for return is "damaged product" and the condition of the product is "damaged," the generation AI will allow the return and refund. If the reason for return is "different from the image" and the condition of the product is "used," the generation AI will reject the return and refund. Step 4: The refund processing unit automatically processes refunds or exchanges based on the reason for return. For example, if the reason for return is "wrong size" and the return is permitted, the generation AI automatically processes refunds. Also, if the reason for return is "damaged product" and the return is permitted, the generation AI automatically processes exchanges. Also, if the reason for return is "different from expectations" and the return is permitted, the generation AI automatically processes refunds. Step 5: The data analysis department analyzes data such as reasons for returns and customer attributes, considers measures to reduce the return rate, and plans measures to improve customer satisfaction. For example, if a particular product is frequently returned, the generation AI will make suggestions to improve the size or description of that product. Also, if the reason for return is that the product is "different from the product description," the generation AI will make suggestions to make the product description more detailed. The generation AI will also plan marketing measures for specific customer segments based on customer attributes.

[0056] (Example 2) The return process automation system according to an embodiment of the present invention is a system that automatically determines the reason for return from the customer's input, automatically determines the condition of the product using image recognition technology, and uses AI to determine whether to allow a return or refund based on the reason for return and the condition of the product, and automatically processes the refund or exchange. As a result, the return process automation system can significantly reduce the time and cost of return operations and improve customer satisfaction.

[0057] The return process automation system according to the embodiment includes a return reason determination unit, a product condition determination unit, a return acceptance determination unit, a refund processing unit, and a data analysis unit. The return reason determination unit determines the reason for return based on the customer's input. For example, if a customer inputs "The size doesn't fit," the generation AI analyzes the information and classifies the reason for return as "Size mismatch." Similarly, if a customer inputs "The product is damaged," the generation AI analyzes the information and classifies the reason for return as "Product damaged." Similarly, if a customer inputs "It's different from what I expected," the generation AI analyzes the information and classifies the reason for return as "Different from what I expected." The product condition determination unit determines the condition of the product using image recognition technology. For example, the generation AI analyzes product images uploaded by customers and determines the product's condition as "New." Similarly, the generation AI analyzes product images uploaded by customers and determines the product's condition as "Used." Similarly, the generation AI analyzes product images uploaded by customers and determines the product's condition as "Damaged." The return acceptance / refund decision unit determines whether to accept a return or refund based on the reason for return and the condition of the product. For example, if the reason for return is "wrong size" and the product condition is "new," the generation AI will accept the return and refund. The generation AI will also accept the return and refund if the reason for return is "damaged product" and the product condition is "damaged." The generation AI will also reject the return and refund if the reason for return is "different from expected" and the product condition is "used." The refund processing unit automatically executes refund and exchange processes based on the reason for return. For example, if the reason for return is "wrong size" and the return is permitted, the generation AI will automatically process a refund. The generation AI will also automatically process an exchange if the reason for return is "damaged product" and the return is permitted. The data analysis unit analyzes data such as return reasons and customer attributes, considers measures to reduce return rates, and develops measures to improve customer satisfaction. For example, if a particular product has a high number of returns, the AI ​​will suggest improving the size or description of that product. Also, if the reason for return is "different from the product description," the AI ​​will suggest making the product description more detailed.Furthermore, the generation AI plans marketing measures for specific customer segments based on customer attributes. As a result, the return process automation system according to the embodiment can significantly reduce the time and cost of return processes and improve customer satisfaction.

[0058] When analyzing a customer's input, the return reason determination unit also references past purchase history and review content, allowing for more accurate determination of return reasons. For example, when the generation AI analyzes a customer's input, the return reason determination unit references past purchase history and, if the same product has been purchased multiple times, checks whether the return reason is consistent. For example, if the reason for returning the same product in the past was "wrong size," it is likely that the reason will be the same this time. Furthermore, when analyzing a customer's input, the return reason determination unit references review content to check how other customers have rated the same product. For example, if another customer reviews the product as "not fitting," the return reason can be classified as "wrong size" based on that information. Furthermore, when analyzing a customer's input, the return reason determination unit integrates past purchase history and review content to more accurately determine return reasons. For example, the return reason can be classified as "wrong size" based on past purchase history and review content. By referencing past purchase history and review content, the accuracy of return reason determination can be improved.

[0059] When determining the reason for return, the return reason determination unit can improve the accuracy of determination by asking questions in real time in response to the customer's input and collecting additional information. For example, the return reason determination unit has the generation AI analyze the customer's input and ask questions in real time if there are any ambiguities. For example, if the customer inputs "the size doesn't fit," the unit will ask "which part specifically doesn't fit" to collect more detailed information. The return reason determination unit also analyzes the customer's input and asks questions in real time if additional information is required. For example, if the customer inputs "the product is damaged," the unit will ask "which part is damaged" to collect more detailed information. The return reason determination unit also improves the accuracy of determination of the reason for return by having the generation AI analyze the customer's input and collect additional information. For example, the unit classifies the reason for return as "incompatible size" based on the additional information. In this way, by asking questions in real time, the accuracy of determination of the reason for return is improved.

[0060] The return reason determination unit uses the emotion estimation function to infer emotions from the customer's input and can determine the reason for return while taking emotional factors into consideration. In the return reason determination unit, for example, the generation AI analyzes the customer's input and infers the customer's emotions using the emotion estimation function. For example, if the input is "very dissatisfied," it is determined that a strong negative emotion is included and the reason for return is classified as "dissatisfied with quality." In addition, the return reason determination unit analyzes the customer's input and infers the customer's emotions using the emotion estimation function. For example, if the input is "not satisfied," it is determined that a negative emotion is included and the reason for return is classified as "disappointed." In addition, the return reason determination unit analyzes the customer's input and infers the customer's emotions using the emotion estimation function, making it possible to determine the reason for return while taking emotional factors into consideration. For example, it uses the emotion estimation function to classify the customer's emotion as "dissatisfied" and the reason for return as "dissatisfied with quality." In this way, using the emotion estimation function makes it possible to determine the reason for return while taking emotional factors into consideration.

[0061] When determining the reason for return, the return reason determination unit can also accept voice input and determine the reason for return using voice recognition technology. In the return reason determination unit, for example, the generation AI accepts voice input and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The size doesn't fit," the voice data is converted into text and the reason for return is classified as "incompatible size." In addition, the return reason determination unit accepts voice input using the generation AI and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The product is damaged," the voice data is converted into text and the reason for return is classified as "damaged product." In addition, the return reason determination unit can more flexibly determine the reason for return by having the generation AI accept voice input and analyze the customer's reason for return using voice recognition technology. For example, the reason for return is classified as "incompatible size" based on the voice input. In this way, by accepting voice input, the reason for return can be more flexibly determined.

[0062] When determining reasons for returns, the return reason determination unit can crawl customer comments on other e-commerce sites and social media to collect related information and use it for determination. For example, the generation AI crawls customer comments on other e-commerce sites and social media to collect related information. For example, if another customer comments about the same product that "the size doesn't fit," the return reason determination unit can classify the reason for return as "mismatched size" based on that information. The return reason determination unit also crawls customer comments on other e-commerce sites and social media to collect related information. For example, if another customer comments about the same product that "the product is damaged," the return reason determination unit can classify the reason for return as "damaged product" based on that information. The return reason determination unit also improves the accuracy of determining reasons for returns by crawling customer comments on other e-commerce sites and social media to collect related information. For example, the return reason determination unit can classify the reason for return as "mismatched size" based on information on other e-commerce sites and social media. By utilizing information from other e-commerce sites and social media, the accuracy of determining reasons for returns can be improved.

[0063] The return reason determination unit can use the emotion estimation function to estimate the emotion a customer expresses when entering the reason for return in real time and make suggestions to elicit positive emotions. For example, in the return reason determination unit, the generation AI analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time. For example, if a customer enters "very dissatisfied," the return reason determination unit asks, "What improvements would make you satisfied?" in order to elicit positive emotions. In addition, the return reason determination unit analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time. For example, if a customer enters "not satisfied," the return reason determination unit asks, "What improvements would make you satisfied?" in order to elicit positive emotions. In addition, the return reason determination unit analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time and make suggestions to elicit positive emotions. For example, the emotion estimation function can classify the customer's emotion as "dissatisfied" and make suggestions to elicit positive emotions. In this way, customer satisfaction is improved by estimating the customer's emotion in real time and eliciting positive emotions.

[0064] When determining the condition of a product, the product condition determination unit can increase the reliability of the determination by also referring to quality information provided by the product's manufacturer or seller. For example, the generation AI in the product condition determination unit determines the condition of the product by referring to quality information provided by the product's manufacturer or seller. For example, the product condition is evaluated based on quality standards provided by the manufacturer. The product condition determination unit also determines the condition of the product by referring to quality information provided by the product's manufacturer or seller. For example, the product condition is evaluated based on quality information provided by the seller. The product condition determination unit also increases the reliability of the determination by referring to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition is determined to be "new" based on quality information from the manufacturer or seller. In this way, by referring to quality information from the manufacturer or seller, the reliability of the determination of the product's condition is improved.

[0065] The product condition determination unit uses the emotion estimation function to estimate the customer's emotion from images uploaded by the customer, and can determine the product condition taking emotional factors into consideration. For example, the product condition determination unit uses the generation AI to analyze images uploaded by the customer and estimate the customer's emotion using the emotion estimation function. For example, if the customer feels "very dissatisfied," the product condition determination unit determines the product condition as "serious defect" taking that emotion into consideration. The product condition determination unit also uses the generation AI to analyze images uploaded by the customer and estimate the customer's emotion using the emotion estimation function. For example, if the customer feels "dissatisfied," the product condition determination unit determines the product condition as "defective" taking that emotion into consideration. The product condition determination unit also uses the generation AI to analyze images uploaded by the customer and estimate the customer's emotion using the emotion estimation function, making it possible to determine the product condition taking emotional factors into consideration. For example, the emotion estimation function is used to classify the customer's emotion as "dissatisfied" and determine the product condition as "defective." This makes it possible to more accurately determine the product condition by taking customer emotions into consideration.

[0066] When determining the condition of a product, the product condition determination unit can also analyze video data and determine the condition of the product based on dynamic information. For example, the generation AI analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video to evaluate the condition. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video to evaluate the condition. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product based on dynamic information. For example, the product condition is determined to be "new" based on the video data. This makes it possible to more accurately determine the condition of a product by analyzing the video data.

[0067] When determining the condition of a product, the product condition determination unit can maintain consistency in its determination by referencing data from when other customers returned the same product. For example, the product condition determination unit determines the condition of the product by referencing data from when the generation AI returned the same product. For example, if the same product was returned in the past due to "dissatisfied quality," the current condition of the product is evaluated based on that information. The product condition determination unit also determines the condition of the product by referencing data from when other customers returned the same product. For example, if the same product was returned in the past due to "size mismatch," the current condition of the product is evaluated based on that information. The product condition determination unit also maintains consistency in its determination by referencing data from when other customers returned the same product. For example, the product condition determination unit determines the condition of the product as "new" based on the return data of other customers. This maintains consistency in the determination of the product condition by referencing the return data of other customers.

[0068] The product condition determination unit can use the emotion estimation function to estimate the emotion a customer expresses in real time when describing the condition of a product and make suggestions to elicit positive emotions. For example, the product condition determination unit uses the generation AI to estimate the emotion a customer expresses in real time when describing the condition of a product and make suggestions to elicit positive emotions. For example, if a customer expresses a feeling of "very dissatisfied," the product condition determination unit asks, "What improvements would make you satisfied?" in order to elicit positive emotions. The product condition determination unit also uses the generation AI to estimate the emotion a customer expresses in real time when describing the condition of a product and make suggestions to elicit positive emotions. For example, if a customer expresses a feeling of "not satisfied," the product condition determination unit asks, "What improvements would make you satisfied?" in order to elicit positive emotions. The product condition determination unit also uses the generation AI to estimate the emotion a customer expresses in real time when describing the condition of a product and make suggestions to elicit positive emotions, thereby improving customer satisfaction. For example, the emotion estimation function can classify the customer's emotion as "dissatisfied" and make suggestions to elicit positive emotions. In this way, customer satisfaction is improved by estimating the customer's emotion in real time and eliciting positive emotions.

[0069] The return acceptance / refund decision unit can learn from past return / refund data to make more accurate decisions when determining whether to accept a return or refund. For example, if the same product was previously returned due to "wrong size," the return acceptance / refund decision unit can use that information to determine whether to accept a return or refund. The return acceptance / refund decision unit can also learn from past return / refund data to determine whether to accept a return or refund. For example, if the same product was previously returned due to "unsatisfactory quality," the return acceptance / refund decision unit can use that information to determine whether to accept a return or refund. The return acceptance / refund decision unit can also improve its decision accuracy by learning from past return / refund data to determine whether to accept a return or refund. For example, it can determine whether to accept a return or refund based on past data. Learning from past data improves the accuracy of return / refund decisions.

[0070] When determining whether to allow a return or refund, the return acceptance determination unit can make a comprehensive decision by taking into account the customer's credit score and past transaction history. For example, the return acceptance determination unit uses the generation AI to refer to the customer's credit score and determine whether to allow a return or refund. For example, a customer with a high credit score is more likely to allow a return or refund. The return acceptance determination unit also uses the generation AI to refer to the customer's credit score and determine whether to allow a return or refund. For example, a customer with a low credit score is more likely to refuse a return or refund. The return acceptance determination unit also uses the generation AI to make a comprehensive decision by taking into account the customer's credit score and past transaction history. For example, it determines whether to allow a return or refund based on the credit score and transaction history. This allows for a more comprehensive decision by taking into account the customer's credit score and transaction history.

[0071] The return acceptance / refund decision unit can use the emotion estimation function to estimate the customer's emotion and consider emotional factors to determine whether to allow a return or refund. For example, the generation AI can estimate the customer's emotion and consider emotional factors to determine whether to allow a return or refund. For example, if a customer feels "very dissatisfied," the return acceptance / refund decision unit can consider those emotions and consider emotional factors to determine whether to allow a return or refund. For example, if a customer feels "dissatisfied," the return acceptance / refund decision unit can use the generation AI to estimate the customer's emotion and consider emotional factors to determine whether to allow a return or refund. This allows for more flexible decisions on whether to allow a return or refund by using the emotion estimation function to classify the customer's emotion as "dissatisfied" and consider emotional factors to determine whether to allow a return or refund. This allows for more flexible decisions on whether to allow a return or refund by considering the customer's emotion.

[0072] When determining whether to allow returns or refunds, the return acceptance determination unit can refer to the return policies and industry standards of other e-commerce sites and adjust its criteria. For example, the generation AI may refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "wrong size," the generation AI may use that information to determine whether to allow returns or refunds. The return acceptance determination unit may also refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "damaged product," the generation AI may use that information to determine whether to allow returns or refunds. The return acceptance determination unit may also refer to the return policies and industry standards of other e-commerce sites to adjust its criteria. For example, the generation AI may determine whether to allow returns or refunds based on information from other e-commerce sites and industry standards. This makes it possible to adjust the criteria by referring to other e-commerce sites and industry standards.

[0073] The return acceptance / refund determination unit uses an emotion estimation function to estimate, in real time, the emotions of customers when they confirm whether they can return or receive a refund, and can make suggestions to elicit positive emotions. For example, the return acceptance / refund determination unit uses a generation AI to estimate, in real time, the emotions of customers when they confirm whether they can return or receive a refund, and can make suggestions to elicit positive emotions. For example, if a customer feels "very dissatisfied," the return acceptance / refund determination unit asks, "What improvements would make you satisfied?" to elicit positive emotions. The return acceptance / refund determination unit also uses a generation AI to estimate, in real time, the emotions of customers when they confirm whether they can return or receive a refund, and can make suggestions to elicit positive emotions. For example, if a customer feels "dissatisfied," the return acceptance / refund determination unit asks, "What improvements would make you satisfied?" to elicit positive emotions. The return acceptance / refund determination unit also improves customer satisfaction by estimating, in real time, the emotions of customers when they confirm whether they can return or receive a refund, and making suggestions to elicit positive emotions. For example, the emotion estimation function classifies the customer's emotions as "dissatisfied" and makes suggestions to elicit positive emotions. This allows the system to estimate customer emotions in real time and elicit positive emotions, thereby improving customer satisfaction.

[0074] When automatically executing refund or exchange processing, the refund processing unit can consider multiple payment methods and delivery methods and select the optimal method. In the refund processing unit, for example, the generation AI considers multiple payment methods and selects the optimal refund method. For example, in the case of credit card payment, it selects refund to the credit card. In addition, the refund processing unit considers multiple payment methods and selects the optimal refund method. For example, in the case of bank transfer, it selects refund to a bank account. In addition, the refund processing unit efficiently performs refund and exchange processing by considering multiple payment methods and delivery methods and selecting the optimal method. For example, it selects the optimal refund method based on the payment method and delivery method. This makes it possible to consider multiple payment methods and delivery methods and perform optimal refund and exchange processing.

[0075] When executing refund or exchange processing, the refund processing unit can perform customized processing by taking into account the customer's past transaction history and preferences. In the refund processing unit, for example, the generation AI references the customer's past transaction history and performs customized refund processing. For example, for a customer who has previously paid by credit card, it prioritizes refunding to the credit card. In addition, the refund processing unit can perform customized refund processing by taking into account the customer's past transaction history and preferences. For example, for a customer who has previously paid by bank transfer, it prioritizes refunding to a bank account. In addition, the refund processing unit can perform customized refund or exchange processing by taking into account the customer's past transaction history and preferences. For example, it selects the optimal refund method based on the transaction history and preferences. This makes it possible to perform customized refund or exchange processing by taking into account the customer's past transaction history and preferences.

[0076] The refund processing unit can use the emotion estimation function to estimate the customer's emotion and execute refund or exchange processing while taking emotional factors into consideration. For example, in the refund processing unit, the generation AI estimates the customer's emotion and executes refund processing while taking emotional factors into consideration. For example, if the customer feels "very dissatisfied," the refund processing unit executes refund processing quickly while taking those emotions into consideration. In addition, the refund processing unit estimates the customer's emotion and executes refund processing while taking emotional factors into consideration. For example, if the customer feels "not satisfied," the refund processing unit executes refund processing quickly while taking those emotions into consideration. In addition, the refund processing unit estimates the customer's emotion and executes refund processing while taking emotional factors into consideration, thereby enabling more flexible refund and exchange processing. For example, the emotion estimation function can classify the customer's emotion as "dissatisfied" and execute prompt refund processing. This enables more flexible refund and exchange processing by taking customer emotions into consideration.

[0077] The refund processing unit can improve the efficiency of processing by strengthening cooperation with other e-commerce sites and logistics companies when executing refund processing and exchange processing. In the refund processing unit, for example, the generation AI cooperates with other e-commerce sites to make refund processing more efficient. For example, it refers to the refund policies of other e-commerce sites to process refunds quickly. In addition, the refund processing unit can improve the efficiency of refund processing by strengthening cooperation with other e-commerce sites and logistics companies. For example, it refers to the refund policies of other e-commerce sites to process refunds quickly. In addition, the refund processing unit can improve the efficiency of refund processing and exchange processing by strengthening cooperation with other e-commerce sites and logistics companies. For example, it selects the optimal refund method based on information from the e-commerce site and logistics company. In this way, cooperation with other e-commerce sites and logistics companies is strengthened, thereby improving processing efficiency.

[0078] The refund processing unit can increase transparency by notifying customers of the progress status in real time when executing refund processing or exchange processing. For example, the refund processing unit builds a system in which the generation AI notifies customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer when the refund processing starts. The refund processing unit also builds a system in which the generation AI notifies customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer when the refund processing is completed. The refund processing unit also increases the transparency of the processing by having the generation AI notify customers of the progress status of the refund processing or exchange processing in real time. For example, it sends a notification to the customer based on the progress status. In this way, by notifying customers of the progress status in real time, the transparency of the processing is increased.

[0079] The refund processing unit can use the emotion estimation function to estimate the emotion of the customer when confirming the refund process or exchange process in real time and make suggestions to elicit positive emotions. For example, the refund processing unit uses the generation AI to estimate the emotion of the customer when confirming the refund process or exchange process in real time and make suggestions to elicit positive emotions. For example, if the customer feels "very dissatisfied," the refund processing unit asks, "What improvements would make you satisfied?" to elicit positive emotions. The refund processing unit also uses the generation AI to estimate the emotion of the customer when confirming the refund process or exchange process in real time and make suggestions to elicit positive emotions. For example, if the customer feels "dissatisfied," the refund processing unit asks, "What improvements would make you satisfied?" to elicit positive emotions. The refund processing unit also uses the generation AI to estimate the emotion of the customer when confirming the refund process or exchange process in real time and make suggestions to elicit positive emotions, thereby improving customer satisfaction. For example, the emotion estimation function classifies the customer's emotion as "dissatisfied" and makes suggestions to elicit positive emotions. In this way, customer satisfaction is improved by estimating the customer's emotion in real time and eliciting positive emotions.

[0080] When conducting data analysis, the data analysis unit can integrate different data sources to perform a more comprehensive analysis. For example, the generation AI integrates social media data and market data to perform data analysis. For example, it integrates customer opinions on social media with market sales data to analyze product reviews. The data analysis unit also integrates different data sources to perform data analysis. For example, it integrates customer data and sales data to analyze customer purchasing behavior. The data analysis unit also integrates different data sources to perform data analysis, making more comprehensive analysis possible. For example, it analyzes product reviews based on social media data, market data, and customer data. In this way, by integrating different data sources, more comprehensive data analysis becomes possible.

[0081] When analyzing data, the data analysis unit can predict trends using time series data and plan future measures. In the data analysis unit, for example, the generation AI uses time series data to predict trends and plan future measures. For example, sales for the next season are predicted based on past sales data. In addition, the data analysis unit uses the generation AI to predict trends using time series data and plan future measures. For example, customer behavior for the next season is predicted based on past customer behavior data. In addition, the data analysis unit uses the generation AI to predict trends using time series data and plan future measures, thereby implementing more effective measures. For example, sales trends are predicted based on time series data and marketing measures for the next season are planned. In this way, trend prediction and future measures can be planned using time series data.

[0082] When analyzing data, the data analysis department compares data from different industries and regions, allowing it to plan measures from a global perspective. For example, the generation AI in the data analysis department compares data from different industries and plans measures from a global perspective. For example, it compares data from the fashion industry and the technology industry to find common trends. The generation AI also compares data from different industries and plans measures from a global perspective. For example, it compares data from the food industry and the electronics industry to find common trends. The data analysis department also compares data from different industries and regions and plans measures from a global perspective, allowing it to implement more effective measures. For example, it plans global marketing measures based on data from different industries and regions. This makes it possible to plan measures from a global perspective by comparing data from different industries and regions.

[0083] When performing data analysis, the data analysis unit can generate visual data and present the results in a form that is visually easy to understand. For example, the data analysis unit uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand. For example, sales data is displayed as a graph. The data analysis unit also uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand. For example, customer behavior data is displayed as a chart. The data analysis unit also uses a generation AI to generate the results of data analysis as visual data and present it in a form that is visually easy to understand, thereby promoting understanding of the data. For example, sales trends are analyzed based on the visual data. In this way, by generating visual data, the results of data analysis can be presented in a form that is visually easy to understand.

[0084] The data analysis unit uses the emotion estimation function to collect customers' emotional reactions to measures in real time and continuously improve the measures based on those reactions. In the data analysis unit, for example, the generation AI collects customers' emotional reactions in real time and continuously improves the measures based on that data. For example, if a customer feels "very dissatisfied," the measures are improved taking into account that emotion. In addition, the data analysis unit collects customers' emotional reactions in real time and continuously improves the measures based on that data. For example, if a customer feels "dissatisfied," the measures are improved taking into account that emotion. In addition, the data analysis unit collects customers' emotional reactions in real time and continuously improves the measures based on that data, thereby improving customer satisfaction. For example, the measures are improved based on the emotional reactions to resolve customer dissatisfaction. In this way, customer satisfaction is improved by collecting customers' emotional reactions in real time and continuously improving the measures.

[0085] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0086] When determining the reason for return, the return reason determination unit can improve the accuracy of determination by asking questions in real time in response to the customer's input and collecting additional information. For example, the generation AI analyzes the customer's input and asks questions in real time if there are any ambiguities. For example, if the customer inputs "The size doesn't fit," the unit will ask "Which part specifically doesn't fit?" to collect more detailed information. The return reason determination unit also analyzes the customer's input and asks questions in real time if additional information is required. For example, if the customer inputs "The product is damaged," the unit will ask "Which part is damaged?" to collect more detailed information. The return reason determination unit also improves the accuracy of determination of the reason for return by having the generation AI analyze the customer's input and collect additional information. For example, the unit may classify the reason for return as "inappropriate size" based on the additional information. This improves the accuracy of determination of the reason for return by asking questions in real time.

[0087] The return reason determination unit uses the emotion estimation function to infer emotions from the customer's input and can determine the reason for return while taking emotional factors into consideration. For example, the generation AI analyzes the customer's input and uses the emotion estimation function to infer the customer's emotions. For example, if the input is "very dissatisfied," it is determined that a strong negative emotion is included and the reason for return is classified as "dissatisfied with quality." The return reason determination unit also analyzes the customer's input and uses the emotion estimation function to infer the customer's emotions. For example, if the input is "not satisfied," it is determined that a negative emotion is included and the reason for return is classified as "disappointed." The return reason determination unit also analyzes the customer's input and uses the emotion estimation function to infer the customer's emotions, making it possible to determine the reason for return while taking emotional factors into consideration. For example, it uses the emotion estimation function to classify the customer's emotion as "dissatisfied" and the reason for return as "dissatisfied with quality." In this way, the emotion estimation function makes it possible to determine the reason for return while taking emotional factors into consideration.

[0088] When determining the reason for return, the return reason determination unit can also accept voice input and determine the reason for return using voice recognition technology. For example, the generation AI accepts voice input and analyzes the customer's reason for return using voice recognition technology. For example, if a customer voice-inputs, "The size doesn't fit," the voice data is converted into text and the reason for return is classified as "size mismatch." The return reason determination unit also accepts voice input using voice recognition technology and analyzes the customer's reason for return. For example, if a customer voice-inputs, "The product is damaged," the voice data is converted into text and the reason for return is classified as "product damaged." The return reason determination unit also accepts voice input using voice recognition technology, allowing for more flexible determination of return reasons. For example, the reason for return is classified as "size mismatch" based on voice input. This allows for more flexible determination of return reasons by accepting voice input.

[0089] The return reason determination unit uses the emotion estimation function to estimate the emotion a customer expresses in real time when entering the reason for return and makes suggestions to elicit positive emotions. For example, the generation AI analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time. For example, if a customer enters "very dissatisfied," the system asks, "What improvements would make you satisfied?" in order to elicit positive emotions. The return reason determination unit also analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time. For example, if a customer enters "not satisfied," the system asks, "What improvements would make you satisfied?" in order to elicit positive emotions. The return reason determination unit also analyzes the customer's input and uses the emotion estimation function to estimate the emotion in real time, making suggestions to elicit positive emotions. For example, the system uses the emotion estimation function to classify the customer's emotion as "dissatisfied" and makes suggestions to elicit positive emotions. In this way, customer satisfaction is improved by estimating the customer's emotion in real time and eliciting positive emotions.

[0090] When determining the condition of a product, the product condition determination unit can increase the reliability of the determination by also referring to quality information provided by the product's manufacturer or seller. For example, the generation AI may refer to quality information provided by the product's manufacturer or seller to determine the condition of the product. For example, the product's condition may be evaluated based on quality standards provided by the manufacturer. The product condition determination unit also increases the reliability of the determination by having the generation AI refer to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition may be evaluated based on quality information provided by the seller. The product condition determination unit also increases the reliability of the determination by having the generation AI refer to quality information provided by the product's manufacturer or seller to determine the product's condition. For example, the product condition may be determined to be "new" based on quality information from the manufacturer or seller. In this way, by referring to quality information from the manufacturer or seller, the reliability of the determination of the product's condition is improved.

[0091] The product condition determination unit uses the emotion estimation function to infer a customer's emotion from images uploaded by the customer, and can determine the product's condition taking emotional factors into account. For example, the generation AI analyzes images uploaded by the customer and uses the emotion estimation function to infer the customer's emotion. For example, if the customer feels "very dissatisfied," the product's condition can be determined as "seriously defective" taking that emotion into account. The product condition determination unit also analyzes images uploaded by the customer and uses the emotion estimation function to infer the customer's emotion. For example, if the customer feels "unsatisfied," the product's condition can be determined as "defective" taking that emotion into account. The product condition determination unit also analyzes images uploaded by the customer and uses the emotion estimation function to infer the customer's emotion, making it possible to determine the product's condition taking emotional factors into account. For example, the emotion estimation function can classify the customer's emotion as "dissatisfied" and determine the product's condition as "defective." This makes it possible to more accurately determine the product's condition by taking customer emotion into account.

[0092] When determining the condition of a product, the product condition determination unit can also analyze video data and determine the condition of the product based on dynamic information. For example, the generation AI analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video and the condition is evaluated. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product. For example, the operation status and feel of the product are checked from the video and the condition is evaluated. The product condition determination unit also analyzes video data uploaded by a customer to determine the condition of the product based on dynamic information. For example, the product condition is determined to be "new" based on the video data. This makes it possible to more accurately determine the condition of a product by analyzing the video data.

[0093] The return acceptance / refund decision unit can use the emotion estimation function to estimate the customer's emotions and consider emotional factors to determine whether to allow a return or refund. For example, the generation AI can estimate the customer's emotions and consider emotional factors to determine whether to allow a return or refund. For example, if a customer feels "very dissatisfied," the return or refund decision unit can consider those emotions to determine whether to allow a return or refund. The return acceptance / refund decision unit can also estimate the customer's emotions and consider emotional factors to determine whether to allow a return or refund. For example, if a customer feels "dissatisfied," the return or refund decision unit can make more flexible decisions by using the generation AI to estimate the customer's emotions and consider emotional factors to determine whether to allow a return or refund. For example, the emotion estimation function can be used to classify the customer's emotions as "dissatisfied" and allow a return or refund. This allows for more flexible decisions on returns and refunds by considering the customer's emotions.

[0094] When determining whether to allow returns or refunds, the return acceptance determination unit can refer to the return policies and industry standards of other e-commerce sites and adjust its criteria. For example, the generation AI can refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "wrong size," the generation AI can use that information to determine whether to allow returns or refunds at present. The return acceptance determination unit can also refer to the return policies of other e-commerce sites to determine whether to allow returns or refunds. For example, if another e-commerce site allows returns for "damaged product," the generation AI can use that information to determine whether to allow returns or refunds at present. The return acceptance determination unit can also refer to the return policies and industry standards of other e-commerce sites to adjust its criteria. For example, the generation AI can determine whether to allow returns or refunds based on information from other e-commerce sites and industry standards. This makes it possible to adjust the criteria by referring to other e-commerce sites and industry standards.

[0095] The refund processing unit can use the emotion estimation function to estimate the customer's emotion and execute refund or exchange processing while taking emotional factors into consideration. For example, the generation AI estimates the customer's emotion and executes refund processing while taking emotional factors into consideration. For example, if the customer feels "very dissatisfied," the refund processing unit performs a prompt refund processing while taking those emotions into consideration. The refund processing unit can also estimate the customer's emotion and execute refund processing while taking emotional factors into consideration. For example, if the customer feels "dissatisfied," the refund processing unit performs a prompt refund processing while taking those emotions into consideration. The refund processing unit can also estimate the customer's emotion and execute refund processing while taking emotional factors into consideration, thereby enabling more flexible refund and exchange processing. For example, the emotion estimation function can classify the customer's emotion as "dissatisfied" and execute a prompt refund processing. This enables more flexible refund and exchange processing by taking customer emotions into consideration.

[0096] The processing flow of the second embodiment will be briefly explained below.

[0097] Step 1: The return reason determination unit determines the reason for return from the customer's input. For example, if a customer inputs "The size doesn't fit," the generation AI analyzes that information and classifies the reason for return as "mismatched size." If a customer inputs "The product is damaged," the generation AI analyzes that information and classifies the reason for return as "damaged product." If a customer inputs "It's different from what I expected," the generation AI analyzes that information and classifies the reason for return as "different from what I expected." Step 2: The product condition determination unit uses image recognition technology to determine the product condition. For example, the generation AI analyzes product images uploaded by customers and determines the product condition as "new." The generation AI also analyzes product images uploaded by customers and determines the product condition as "used." The generation AI also analyzes product images uploaded by customers and determines the product condition as "damaged." Step 3: The return acceptance / refund decision unit determines whether to accept a return or refund based on the reason for return and the condition of the product. For example, if the reason for return is "wrong size" and the condition of the product is "new," the generation AI will allow the return and refund. If the reason for return is "damaged product" and the condition of the product is "damaged," the generation AI will allow the return and refund. If the reason for return is "different from the image" and the condition of the product is "used," the generation AI will reject the return and refund. Step 4: The refund processing unit automatically processes refunds or exchanges based on the reason for return. For example, if the reason for return is "wrong size" and the return is permitted, the generation AI automatically processes refunds. Also, if the reason for return is "damaged product" and the return is permitted, the generation AI automatically processes exchanges. Also, if the reason for return is "different from expectations" and the return is permitted, the generation AI automatically processes refunds. Step 5: The data analysis department analyzes data such as reasons for returns and customer attributes, considers measures to reduce the return rate, and plans measures to improve customer satisfaction. For example, if a particular product is frequently returned, the generation AI will make suggestions to improve the size or description of that product. Also, if the reason for return is that the product is "different from the product description," the generation AI will make suggestions to make the product description more detailed. The generation AI will also plan marketing measures for specific customer segments based on customer attributes.

[0098] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0099] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0100] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0104] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0105] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0106] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0107] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0108] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0109] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0110] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0111] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0112] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0116] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0117] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0126] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0132] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0139] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0140] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0141] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0142] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0143] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0144] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0145] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0147] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0148] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0149] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0150] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0151] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0152] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0153] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0154] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0155] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0156] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0157] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0158] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0159] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0160] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0161] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0162] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0163] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0164] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a return reason determination unit that determines the reason for return based on the customer's input; a product condition determination unit that determines the condition of the product based on the reason for return determined by the reason for return determination unit; a return acceptance / refund determination unit that determines whether or not to accept a return or refund based on the condition of the product determined by the product condition determination unit; a refund processing unit that automatically executes a refund process or an exchange process based on the reason for return determined by the return acceptance determination unit; a data analysis unit that analyzes data such as the reasons for return and customer attributes, considers measures to reduce the return rate, and plans measures to improve customer satisfaction. A system characterized by:

2. The return reason determination unit When determining the reason for return, questions are posed in real time to the customer's input to collect additional information and improve the accuracy of the determination.

2. The system of claim 1.

3. The commodity state determination unit When using image recognition technology to determine the condition of the product, multiple images are analyzed and information from different angles is integrated to improve the accuracy of the determination.

2. The system of claim 1.

4. The return acceptance determination unit When determining whether to accept a return or refund, the system learns from past return and refund data to make more accurate decisions.

2. The system of claim 1.

5. The refund processing unit: When carrying out the refund or exchange process, the customer's past transaction history and preferences are taken into consideration to perform a customized process.

2. The system of claim 1.

6. The data analysis unit Using the emotion estimation function, the emotional data of the customer is analyzed, and measures are developed taking into account emotional factors.

2. The system of claim 1.

7. The return reason determination unit Using an emotion estimation function, the emotion is estimated from the input content of the customer, and the reason for return is determined taking into consideration emotional factors.

2. The system of claim 1.

8. The commodity state determination unit Using an emotion estimation function, the emotion is estimated from the image uploaded by the customer, and the state of the product is determined taking into account emotional factors.

2. The system of claim 1.

Images